From: Dan Williams <dan.j.williams@intel.com>
To: Christoph Hellwig <hch@lst.de>
Cc: Vishal Verma <vishal.l.verma@intel.com>,
Dave Jiang <dave.jiang@intel.com>,
Alasdair Kergon <agk@redhat.com>,
Mike Snitzer <snitzer@redhat.com>,
Ira Weiny <ira.weiny@intel.com>,
Heiko Carstens <hca@linux.ibm.com>,
Vasily Gorbik <gor@linux.ibm.com>,
Christian Borntraeger <borntraeger@de.ibm.com>,
Vivek Goyal <vgoyal@redhat.com>,
Stefan Hajnoczi <stefanha@redhat.com>,
Miklos Szeredi <miklos@szeredi.hu>,
Matthew Wilcox <willy@infradead.org>,
device-mapper development <dm-devel@redhat.com>,
Linux NVDIMM <nvdimm@lists.linux.dev>,
linux-s390 <linux-s390@vger.kernel.org>,
linux-fsdevel <linux-fsdevel@vger.kernel.org>,
virtualization@lists.linux-foundation.org
Subject: Re: [PATCH 5/5] dax: always use _copy_mc_to_iter in dax_copy_to_iter
Date: Sun, 12 Dec 2021 07:03:02 -0800 [thread overview]
Message-ID: <CAPcyv4gYXqbNRLkM4zJUq=sZuw4h_T+BSTXmESXc8juiWijKbQ@mail.gmail.com> (raw)
In-Reply-To: <20211209063828.18944-6-hch@lst.de>
On Wed, Dec 8, 2021 at 10:38 PM Christoph Hellwig <hch@lst.de> wrote:
>
> While using the MC-safe copy routines is rather pointless on a virtual device
> like virtiofs, it also isn't harmful at all. So just use _copy_mc_to_iter
> unconditionally to simplify the code.
From a correctness perspective, yes, but from a performance perspective, see:
enable_copy_mc_fragile()
...on those platforms fast-string copy implementation is replaced with
a manual unrolled copy. So this will cause a performance regression on
those platforms.
How about let's keep this as is / still only use it for PMEM where end
users are already dealing with the performance difference across
platforms? I considered exporting an indicator of which backend
routine has been selected from arch/x86/lib/copy_mc.c, but it got
messy quickly so I fell back to just keeping the status quo.
prev parent reply other threads:[~2021-12-12 15:03 UTC|newest]
Thread overview: 33+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-12-09 6:38 devirtualize kernel access to DAX Christoph Hellwig
2021-12-09 6:38 ` [PATCH 1/5] uio: remove copy_from_iter_flushcache() and copy_mc_to_iter() Christoph Hellwig
2021-12-12 14:22 ` Dan Williams
2021-12-13 8:27 ` Christoph Hellwig
2021-12-09 6:38 ` [PATCH 2/5] dax: simplify dax_synchronous and set_dax_synchronous Christoph Hellwig
2021-12-09 21:03 ` Pankaj Gupta
2021-12-12 14:23 ` Dan Williams
2021-12-09 6:38 ` [PATCH 3/5] dax: remove the DAXDEV_F_SYNC flag Christoph Hellwig
2021-12-12 14:24 ` Dan Williams
2021-12-13 8:40 ` Pankaj Gupta
2021-12-09 6:38 ` [PATCH 4/5] dax: remove the copy_from_iter and copy_to_iter methods Christoph Hellwig
2021-12-10 14:16 ` Vivek Goyal
2021-12-12 14:44 ` Dan Williams
2021-12-13 8:23 ` Christoph Hellwig
2021-12-14 14:22 ` Vivek Goyal
2021-12-14 16:41 ` Dan Williams
2021-12-14 20:32 ` Vivek Goyal
2021-12-14 23:43 ` Dan Williams
2021-12-15 15:52 ` Vivek Goyal
2021-12-15 16:46 ` Dan Williams
2021-12-15 10:30 ` Stefan Hajnoczi
2021-12-15 15:43 ` Vivek Goyal
2021-12-15 17:27 ` Stefan Hajnoczi
2021-12-13 16:17 ` Vivek Goyal
2021-12-12 14:39 ` Dan Williams
2021-12-13 8:24 ` Christoph Hellwig
2021-12-09 6:38 ` [PATCH 5/5] dax: always use _copy_mc_to_iter in dax_copy_to_iter Christoph Hellwig
2021-12-10 14:05 ` Vivek Goyal
2021-12-12 14:48 ` Dan Williams
2021-12-13 8:20 ` Christoph Hellwig
2021-12-13 16:43 ` Dan Williams
2021-12-14 13:59 ` Vivek Goyal
2021-12-12 15:03 ` Dan Williams [this message]
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to='CAPcyv4gYXqbNRLkM4zJUq=sZuw4h_T+BSTXmESXc8juiWijKbQ@mail.gmail.com' \
--to=dan.j.williams@intel.com \
--cc=agk@redhat.com \
--cc=borntraeger@de.ibm.com \
--cc=dave.jiang@intel.com \
--cc=dm-devel@redhat.com \
--cc=gor@linux.ibm.com \
--cc=hca@linux.ibm.com \
--cc=hch@lst.de \
--cc=ira.weiny@intel.com \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-s390@vger.kernel.org \
--cc=miklos@szeredi.hu \
--cc=nvdimm@lists.linux.dev \
--cc=snitzer@redhat.com \
--cc=stefanha@redhat.com \
--cc=vgoyal@redhat.com \
--cc=virtualization@lists.linux-foundation.org \
--cc=vishal.l.verma@intel.com \
--cc=willy@infradead.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).